© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27160
    Prev
    Next
    INDEX
    Explanations

    report data or bugs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÙĤ
    -0.10
    åĪĨ解
    -0.09
    çĽ¼
    -0.08
    è·Į
    -0.08
    æ¶īåıĬåĪ°
    -0.08
    æ¯Ķäºļ
    -0.08
    æĹłåħ³
    -0.08
    å¾Īæĥ³
    -0.08
    æIJ¬åĪ°
    -0.08
    大åħ¨
    -0.08
    POSITIVE LOGITS
    æĬ¥åijĬ
    0.20
    æ±ĩæĬ¥
    0.19
    åĽŀæĿ¥
    0.19
    åł±åijĬ
    0.19
     report
    0.17
    带åĽŀ
    0.17
    åĽŀä¾Ĩ
    0.16
    å½ĴæĿ¥
    0.16
     reporting
    0.16
     reports
    0.16
    Activations Density 0.076%

    No Known Activations